MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answering
This work addresses document question answering, particularly for tasks involving child-relationship understanding, but it is incremental as it adapts an existing summarizer.
The paper tackled document question answering by adapting an efficient long document extractive summarizer, MemSum, to selectively extract text blocks as answers, resulting in a 9% improvement in exact match accuracy over prior state-of-the-art baselines.
We introduce MemSum-DQA, an efficient system for document question answering (DQA) that leverages MemSum, a long document extractive summarizer. By prefixing each text block in the parsed document with the provided question and question type, MemSum-DQA selectively extracts text blocks as answers from documents. On full-document answering tasks, this approach yields a 9% improvement in exact match accuracy over prior state-of-the-art baselines. Notably, MemSum-DQA excels in addressing questions related to child-relationship understanding, underscoring the potential of extractive summarization techniques for DQA tasks.